Week 5 Individual Assignment: Process Improvement Plan
Justin Sciarro
OPS 571
November 26, 2012
Barry Haigh

Process Improvement Plan
During week one the process of pulling patient room trash and linen was analyzed. The steps included the designing of a flowchart outlining the steps of the actual process, while identifying factors and metrics. The remainder of this paper will focus on process improvement as it relates to control limits and confidence intervals.
Moving on, in this case, process control is concerned with monitoring quality while the service is being performed (Chase, Jacobs, & Aquilano, 2006). The two types of variation within processes are assignable and common. Assignable variation is defined by factors that can be clearly identified and perhaps even managed, while common variation or random variation is simply natural in the process itself (Chase, Jacobs, & Aquilano, 2006). Regarding the process of pulling patient room trash and linen, assignable variation included collection/disposal methods and trash liner compatibility/fit. After evaluating these variations, it was determined they could be effectively managed through alternative options. For example, since the trash and linen is collected using separate receptacles, the linen is left in a staging area where it is picked up by a third party vendor each evening. However, the trash, once collected, is disposed of into a large compactor. This particular task can be time consuming; therefore, it was determined the disposal of the trash could be assigned to another employee. Moving on, the trash liners being used for the patient room receptacles were too small; therefore, causing the liner to collapse into the container resulting in a mess. This particular variation has been managed through the implementation of larger liners. On the other hand, common variation included patient census or volume and the amount of trash and linen in each patient room. Increased amounts meant increased trips, which resulted in more time to complete the process.
Statistical process control involves testing a random sample of output from a process to determine whether a process is producing items within a preselected range (Chase, Jacobs, & Aquilano, 2006, p. 354). For this process times were recorded over a five week time period resulting in 25 samples. The times produced statistical information such as the mean, standard deviation and range. Knowing that, week one had a total process time of 445 minutes, mean of 89, standard deviation of 6.44 and range of 17. Week two had a total process time of 466 minutes, mean of 93, standard deviation of 5.26 and range of 14. Week three had a total process time of 350 minutes, mean of 70, standard deviation of 3.39 and range of 9. Week four had a total process time of 324 minutes, mean of 65, standard deviation of 3.49 and range of 9. Lastly, week five had a total process time of 292 minutes, mean of 58, standard deviation of 1.95 and range of 5.
When calculating the upper and lower control limits for this process several calculations were required. First, the mean of the weekly total minutes was 75. Next, the mean was subtracted from each data point (89-75, 93-75, 70-75, 65-75, 58-75) and then squared. From there the mean was calculated again resulting in 187, which has a standard deviation of 13.67. Multiplying the standard deviation by 3 and adding the mean of the original data set (75) provides an upper control limit of 116. The lower control limit was reached by subtracting 41 from 75, which is calculated at 34.
It is critical to understand that these control limits are connected to process capability rather than tolerances or limits. Process capability measures the goodness of a process, comparing the voice of the process with the voice of the customer, while the voice of the customer here is the specification range (tolerance) and/or the nearest customer specification limit (Neubauer, 2011). Process capability is closely connected to Six Sigma, which is an approach centralized around increased efficiency and quality as it relates to products/services and processes. More specifically, Six Sigma and process capability focuses on defects, which can be defined as any component that does not fall within the customer’s specification limits (Chase, Jacobs, & Aquilano, 2006).
What conclusions can be drawn from the above information? The management of the assignable variations significantly impacted the duration or time of the process. Changes in variations took place during the third week of data collection. As a result, total process time decreased and ultimately distorted the upper and lower control limits. Moving forward, one should expect the process time (or data) to be recorded somewhere right around 60 minutes or one hour. Knowing that confidence intervals signify a degree of certainty within estimates, as more and more samples are collected and recorded using the same procedure, it would be safe to assume the confidence intervals would hold the average of all the estimates 90% - 95% of the time. Lastly, seasonal factors do not prove to impact the process of pulling patient room trash and linen. Census could potentially have a significant impact on the process; however, it is very difficult to forecast volume within healthcare, especially from a seasonal perspective.

References
Chase, R. B., Jacobs, F. R., & Aquilano, N. J. (2006) Operations management for competitive advantage (11th ed). New York: McGraw Hill/Irwin.

Neubauer, D. (2011). Understanding Process Capability. Retrieved from http://www.astm.org/standardization-news/data-points/understanding-process-capability-mj11.html